CN106557389A - A kind of slow disk detection method and device - Google Patents
A kind of slow disk detection method and device Download PDFInfo
- Publication number
- CN106557389A CN106557389A CN201510634651.0A CN201510634651A CN106557389A CN 106557389 A CN106557389 A CN 106557389A CN 201510634651 A CN201510634651 A CN 201510634651A CN 106557389 A CN106557389 A CN 106557389A
- Authority
- CN
- China
- Prior art keywords
- hard disk
- requests
- disk
- different types
- service time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
Abstract
The embodiment of the present invention provides a kind of slow disk detection method and device, is related to field of computer technology, can solve the problem that the low problem of slow disk detection degree of accuracy.Its method is：By the average service time of the corresponding input and output I/O requests of different types of hard disk in the acquisition current preset cycle, further according to the average service time slow disk threshold value corresponding with the different types of hard disk of the next predetermined period of the Relation acquisition of preset value of the corresponding I/O requests of different types of hard disk, and then the slow disk in next predetermined period is determined according to the average service time of the corresponding slow disk threshold value of different types of hard disk I/O requests corresponding with each hard disk in next predetermined period.The embodiment of the present invention is used for the slow disk threshold value of dynamic adjustment.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of slow disk detection method and device.
Background technology
Disc array system may include multigroup RAID (Redundant Array of
Independent Disks, RAID), its RAID is a kind of hard disk (physics polylith independence
Hard disk) it is combined in different ways the hard disk groups (logic hard disk) for being formed.By number
According to being placed on multiple hard disks, the mode of input-output operation symmetrical is overlapped, improved performance, so as to
The storage performance higher than single hard disk is provided and technology of data copy is provided.Meanwhile, in storage data
When, data are cut into into many sections, is stored on each hard disk respectively.
For the disc array system, when occurring in system, hard disk is aging, magnetic head is degenerated, hard disk
Hard disk response speed can be caused slack-off during various situations such as bad track, and as data are cut into multiple sections
It is stored on each hard disk respectively, thus can ties down whole system as the response of one piece of hard disk is slack-off
Response speed, accordingly, it would be desirable to input/output periodically or non-periodically to hard disk (input/output,
I/O) response time is monitored, to determine slow disk according to I/O response times and then slow to this
Disk implements the related measures such as RAID reconstruction, hard disk isolation.
At present, the mode for detecting slow disk is one threshold values of setting mostly, cycle regular hour or
In multiple identical time cycles, if the threshold value that the average service time of the I/O requests of hard disk reaches,
Then assert that the hard disk is slow disk.Wherein, the average service time of I/O requests is to send in the time cycle
N I/O response time meansigma methodss.But, for different types of service, I/O requests are visited
Ask that pressure size is different, the slow moushroom valve value of identical cannot adapt to miscellaneous service demand；It is hard for different
Disc-type, its I/O response time are also different so that the slow moushroom valve value of identical cannot also adapt to inhomogeneity
The hard disk of type, or even hard disk, after different service times, its degree of aging is also not quite similar, if
Using the slow moushroom valve value of identical, then real problematic hard disk cannot be accurately positioned out, therefore, it is this
The degree of accuracy of slow disk detection method is low.
The content of the invention
The embodiment of the present invention provides a kind of slow disk detection method and device, can solve the problem that slow disk detection is accurate
The low problem of degree.
A kind of first aspect, there is provided detection method of slow disk, including：
Obtain the average of the corresponding input and output I/O requests of different types of hard disk in the current preset cycle
Service time；
According to the relation of the average service time and preset value of the corresponding I/O requests of different types of hard disk
Obtain the corresponding slow disk threshold value of the different types of hard disk of next predetermined period；
According in the corresponding slow disk threshold value of different types of hard disk and next predetermined period, each is hard
The average service time of the corresponding I/O requests of disk determines the slow disk in next predetermined period.
With reference in a first aspect, in the first mode in the cards of first aspect, the acquisition is worked as
The average service time bag of the corresponding input and output I/O requests of different types of hard disk in front predetermined period
Include：
Obtain the average service time of the corresponding I/O requests of each hard disk in the current preset cycle
Meansigma methodss；
Obtain the quantity of the I/O requests that described each hard disk correspondence is received in the current preset cycle
Account for the ratio of the total amount of the I/O requests that the corresponding all hard disks of the affiliated type of described each hard disk are received
Rate；
Obtained according to the meansigma methodss and the ratio of each hard disk in different types of hard disk
The average service time of the corresponding I/O requests of different types of hard disk in the current preset cycle.
With reference to the first mode in the cards of first aspect, second in first aspect may be real
It is in existing mode, described to obtain the flat of the corresponding I/O requests of each hard disk in the current preset cycle
The meansigma methodss of service time include：
Obtain the response of the I/O requests that described each hard disk correspondence is received in the current preset cycle
Time sum；
It is corresponding according to the response time sum each hard disk described in the current preset cycle
The ratio of I/O request numbers obtains the corresponding I/O requests of each hard disk in the current preset cycle
The meansigma methodss of average service time.
With reference to the first mode in the cards of first aspect, the third in first aspect may be real
It is in existing mode, described to obtain the flat of the corresponding I/O requests of each hard disk in the current preset cycle
The meansigma methodss of service time include：
The corresponding I/O requests of each hard disk described in obtaining in the unit interval in the current preset cycle
Average service time sum；
According to the ratio of the average service time sum and the number of the unit interval is obtained
The meansigma methodss of the average service time of the corresponding I/O requests of each hard disk in the current preset cycle.
With reference to first aspect the first mode in the cards to the third mode in the cards,
In 4th kind of mode in the cards of first aspect, each according in different types of hard disk
The meansigma methodss of hard disk and the ratio obtain different types of hard in the current preset cycle
The average service time of the corresponding I/O requests of disk includes：
The meansigma methodss of each hard disk in different types of hard disk and the ratio are weighted
When obtaining the average service of the corresponding I/O requests of different types of hard disk in the current preset cycle
Between；
Wherein, if the corresponding I/O of any type of hard disk in different types of hard disk requests it is average
It is expressed as AvgT service times, then AvgT=X1*Z1+X2*Z2+…Xn*Zn, X1Represent any kind
Hard disk in the 1st corresponding meansigma methodss of hard disk, Z1The 1st corresponding ratio of hard disk is represented,
X2Represent the 2nd corresponding meansigma methodss of hard disk in any type of hard disk, Z2Represent described
The corresponding ratio of 2 hard disks, XnRepresent that n-th hard disk in any type of hard disk is corresponding
Meansigma methodss, ZnRepresent the corresponding ratio of n-th hard disk.
With reference in a first aspect, in the 5th kind of mode in the cards of first aspect, the basis is not
The average service time of the corresponding I/O requests of hard disk of same type is next with the Relation acquisition of preset value pre-
If the corresponding slow disk threshold value of cycle different types of hard disk includes：
According to the product of the average service time and preset value of the corresponding I/O requests of different types of hard disk
Obtain the corresponding slow disk threshold value of the different types of hard disk of next predetermined period.
With reference in a first aspect, in the 6th kind of mode in the cards of first aspect, methods described is also
Including：
It is in first predetermined period after electricity on storage array, corresponding just according to different types of hard disk
The average service time of beginning threshold value I/O requests corresponding with described each hard disk determines different types of hard
Slow disk in disk.
A kind of second aspect, there is provided device of slow disk detection, including：
Acquiring unit, for obtaining the corresponding input and output of different types of hard disk in the current preset cycle
The average service time of I/O requests；
The acquiring unit, is additionally operable to the average clothes according to the corresponding I/O requests of different types of hard disk
Business time slow disk threshold corresponding with the different types of hard disk of the next predetermined period of the Relation acquisition of preset value
Value；
Determining unit, for next default with described according to the corresponding slow disk threshold value of different types of hard disk
During in cycle, the average service time of the corresponding I/O requests of each hard disk determines next predetermined period
Slow disk.
It is with reference to second aspect, in the first mode in the cards of second aspect, described to obtain single
Unit specifically for：
Obtain the average service time of the corresponding I/O requests of each hard disk in the current preset cycle
Meansigma methodss；
Obtain the quantity of the I/O requests that described each hard disk correspondence is received in the current preset cycle
Account for the ratio of the total amount of the I/O requests that the corresponding all hard disks of the affiliated type of described each hard disk are received
Rate；
Obtained according to the meansigma methodss and the ratio of each hard disk in different types of hard disk
The average service time of the corresponding I/O requests of different types of hard disk in the current preset cycle.
With reference to the first mode in the cards of second aspect, second in second aspect may be real
In existing mode, the acquiring unit specifically for：
Obtain the response of the I/O requests that described each hard disk correspondence is received in the current preset cycle
Time sum；
It is corresponding according to the response time sum each hard disk described in the current preset cycle
The ratio of I/O request numbers obtains the corresponding I/O requests of each hard disk in the current preset cycle
The meansigma methodss of average service time.
With reference to the first mode in the cards of second aspect, the third in second aspect may be real
In existing mode, the acquiring unit specifically for：
The acquiring unit specifically for：
The corresponding I/O requests of each hard disk described in obtaining in the unit interval in the current preset cycle
Average service time sum；
According to the ratio of the average service time sum and the number of the unit interval is obtained
The meansigma methodss of the average service time of the corresponding I/O requests of each hard disk in the current preset cycle.
With reference to second aspect the first mode in the cards to the third mode in the cards,
In 4th kind of mode in the cards of second aspect, the acquiring unit specifically for：
The meansigma methodss of each hard disk in different types of hard disk and the ratio are weighted
When obtaining the average service of the corresponding I/O requests of different types of hard disk in the current preset cycle
Between；
Wherein, if the corresponding I/O of any type of hard disk in different types of hard disk requests it is average
It is expressed as AvgT service times, then AvgT=X1*Z1+X2*Z2+…Xn*Zn, X1Represent any kind
Hard disk in the 1st corresponding meansigma methodss of hard disk, Z1The 1st corresponding ratio of hard disk is represented,
X2Represent the 2nd corresponding meansigma methodss of hard disk in any type of hard disk, Z2Represent described
The corresponding ratio of 2 hard disks, XnRepresent that n-th hard disk in any type of hard disk is corresponding
Meansigma methodss, ZnRepresent the corresponding ratio of n-th hard disk.
It is with reference to second aspect, in the 5th kind of mode in the cards of second aspect, described to obtain single
Unit specifically for：
According to the product of the average service time and preset value of the corresponding I/O requests of different types of hard disk
Obtain the corresponding slow disk threshold value of the different types of hard disk of next predetermined period.
It is with reference to second aspect, in the 6th kind of mode in the cards of second aspect, described to determine list
Unit is additionally operable to：
It is in first predetermined period after electricity on storage array, corresponding just according to different types of hard disk
The average service time of beginning threshold value I/O requests corresponding with described each hard disk determines different types of hard
Slow disk in disk.
The embodiment of the present invention provides a kind of slow disk detection method and device, by obtaining the current preset cycle
The average service time of the corresponding input and output I/O requests of interior different types of hard disk, further according to difference
The average service time of the corresponding I/O requests of hard disk of type is next with the Relation acquisition of preset value default
The corresponding slow disk threshold value of cycle different types of hard disk, so it is corresponding slow according to different types of hard disk
The average service time of disk threshold value I/O requests corresponding with each hard disk in next predetermined period determines institute
The slow disk in next predetermined period is stated, thus, the present invention can be according to inhomogeneity in the current preset cycle
The average service time of the hard disk of type determines the slow disk threshold value of next predetermined period, so can be to difference
The hard disk of type formulates the slow disk threshold values of differentiation due to the difference of the average service time of its I/O,
Due to the I/O response times difference of hard disk different service types, the I/O of the hard disk of the different lengths of service
Response time it is also different, cause the average service time of the I/O of hard disk different so that the present invention this
The differentiation determination for planting slow disk threshold value does lateral comparison equivalent to the hard disk in system, therefore, this
The slow disk threshold value of bright different types of differentiation also can adapt to different service types and different service years
The hard disk of limit, can be according to the hard disk of different hard disk types, different service types and the different lengths of service
Differentiation solve the problems, such as that slow disk detection degree of accuracy is low, improve the degree of accuracy of slow disk detection.
Description of the drawings
In order to be illustrated more clearly that the technical scheme of the embodiment of the present invention, below will be to embodiment or existing
Accompanying drawing to be used needed for technology description is briefly described, it should be apparent that, in describing below
Accompanying drawing is only some embodiments of the present invention, for those of ordinary skill in the art, is not being paid
On the premise of going out creative work, can be with according to these other accompanying drawings of accompanying drawings acquisition.
Fig. 1 is a kind of schematic flow sheet of slow disk detection method provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic flow sheet of slow disk detection method provided in an embodiment of the present invention；
Fig. 3 is a kind of device of slow disk detection provided in an embodiment of the present invention.
Fig. 4 is a kind of device of slow disk detection provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, to the technical scheme in the embodiment of the present invention
It is clearly and completely described, it is clear that described embodiment is only that a present invention part is real
Apply example, rather than the embodiment of whole.Based on the embodiment in the present invention, ordinary skill
The every other embodiment obtained under the premise of creative work is not made by personnel, belongs to this
The scope of invention protection.
The embodiment of the present invention provides a kind of slow disk detection method, and the executive agent of the present embodiment is slow for detection
The processing meanss of disk, the device can be being realized by the way of hardware and/or software, it is preferred that should
Processing meanss can be arranged on and be loaded with the array system of hard disk, be easy to the hard disk in array system
Detected, as shown in figure 1, including：
101st, the corresponding input and output I/O requests of different types of hard disk in the current preset cycle are obtained
Average service time.
The device detected for slow disk can first determine that the hard disk type in array system, and for example, this is hard
Disc-type can include solid state hard disc (Solid State Drives, SSD), Serial Attached SCSI (SAS)
(Serial Attached Small computer system interface, SAS), near line
SAS (Near Line_SAS, NL_SAS) and serial port hard disk (Serial Advanced Technology
Attachment, SATA) etc., then obtain I/O of each type of hard disk within the current preset cycle
The average service time of request.
Generally, for single hard disk, the average service time of I/O requests refers to the single hard disk
The meansigma methodss of the response time of the multiple I/O request received in 1s, the response time of I/O requests is
Refer to hard disk from receive I/O request reach array system when play service at the end of till time.
And after hard disk is classified, according to hard disk type, obtain each class hard disk within the current preset cycle
The average service time of I/O requests.Wherein, predetermined period can be one hour, or other
Value, the application are not limited.
102nd, the average service time and preset value according to the corresponding I/O requests of different types of hard disk
The corresponding slow disk threshold value of the different types of hard disk of the next predetermined period of Relation acquisition.
In the embodiment of the present invention, it is assumed that in the array system, if the I/O of one or several hard disks
Response time is bigger than the weighted mean of the I/O response times of other hard disks, and numerically presents again
Number trend, then this hard disk or these hard disks are considered as into slow disk, namely the concept of slow disk be by
Which does a lateral comparison with other all hard disks.
As the average service time that the I/O of hard disk is asked is that the I/O for receiving in the unit time please
The meansigma methodss of the response time asked, and hard disk is classification, then the determination of slow disk threshold value can be not
When the hard disk of same type obtains the average service of the corresponding I/O requests of different type by weighting algorithm
Between, i.e. weighted mean, then when the average service time that the I/O of hard disk is asked can be than its institute
The weighted mean of the hard disk of category type is defined as slow disk when being higher by multiple.Then, here according to difference
The average service time of the corresponding I/O requests of hard disk of type is next with the Relation acquisition of preset value default
The corresponding slow disk threshold value of cycle different types of hard disk can include：According to different types of hard disk correspondence
I/O requests average service time and preset value product, obtain next predetermined period different type
The corresponding slow disk threshold value of hard disk.Here preset value rule of thumb may be configured as 10, be alternatively certainly
Other values, the application are not limited.
103rd, according in the corresponding slow disk threshold value of different types of hard disk and next predetermined period, each is hard
The average service time of the corresponding I/O requests of disk determines the slow disk in next predetermined period.
According to next predetermined period after the slow disk threshold value of different types of hard disk, in next default week
In phase, can be according to belonging to the average service time of the requests of the I/O in the certain hour of each hard disk be with which
The slow disk threshold value of the hard disk of type is compared, if during the average service of the I/O requests of arbitrary hard disk
Between more than or equal to its affiliated type hard disk slow disk threshold value, then can determine that arbitrary hard disk is slow
Disk.Here certain hour is referred in next predetermined period, is obtained at regular intervals once arbitrary
The average service time of the I/O requests that hard disk is received within a certain period of time, such as, certain hour is
5min, predetermined period are one hour.
The embodiment of the present invention provides a kind of slow disk detection method, different in the current preset cycle by obtaining
The average service time of the corresponding input and output I/O requests of hard disk of type, further according to different types of
The average service time of the corresponding I/O requests of hard disk is with the next predetermined period of Relation acquisition of preset value not
The corresponding slow disk threshold value of hard disk of same type, and then according to the corresponding slow disk threshold value of different types of hard disk
The average service time of I/O requests corresponding with each hard disk in next predetermined period determines next default
Slow disk in cycle, thus, the present invention can be according to different types of hard disk in the current preset cycle
Average service time determines the slow disk threshold value of next predetermined period, so can be to different types of hard disk
Due to the different slow disk threshold values for formulating differentiation of the average service time of its I/O, also due to hard disk is not
I/O response times with type of service are different, the response time of the I/O of the hard disk of the different lengths of service
Also it is different, cause the average service time of the I/O of hard disk different so that this slow disk threshold value of the present invention
Differentiation determine do lateral comparison equivalent to the hard disk in system, therefore, different type of the present invention
The slow disk threshold value of differentiation also can adapt to the hard disk of different service types and the different lengths of service, energy
The differentiation of enough hard disks according to different hard disk types, different service types and the different lengths of service is solved
The low problem of slow disk detection degree of accuracy, improves the degree of accuracy of slow disk detection.
Below above-described embodiment is specifically described.
The embodiment of the present invention provides a kind of slow disk detection method, as shown in Fig. 2 including：
201st, in first predetermined period after electricity on storage array, according to different types of hard disk pair
The average service time of the initial threshold answered I/O requests corresponding with each hard disk determines different types of
Slow disk in hard disk.
If the storage array just goes up electricity, the slow disk threshold of different types of hard disk in first predetermined period
Value can determine according to default initial threshold that the initial threshold can be according to test data and existing network business feelings
Condition is formulated, and predetermined period can for example be one hour etc..It is average that the I/O of any of which hard disk is asked
Service time can be the average of the response time of I/O request of the arbitrary hard disk within a period of time
Value, a period of time can for example be 5min etc., i.e., the I/O of arbitrary hard disk is obtained once every 5min
The average service time of request, and be compared with the initial threshold of the hard disk of its affiliated type, if
More than initial threshold, it is determined that for slow disk.
Then, different types of hard disk in the current preset cycle can be obtained by weighted calculation corresponding defeated
Enter to export the average service time of I/O requests, specifically can be realized by step 202 to step 204.
202nd, obtain the average service time of the corresponding I/O requests of each hard disk in the current preset cycle
Meansigma methodss.
Specifically, the crash time between current preset cycle and next predetermined period, obtain current pre-
If the meansigma methodss of the average service time of the corresponding I/O of each hard disk in cycle requests, such as the
One predetermined period and the crash time of second predetermined period, obtain each in first predetermined period
The meansigma methodss of the average service time of the corresponding I/O requests of hard disk.
Exemplary, the I/O requests that each hard disk correspondence is received in the current preset cycle can be obtained
Response time sum, according to response time sum I/O corresponding with each hard disk in the current preset cycle
The ratio of request number obtains the average service of the corresponding I/O requests of each hard disk in the current preset cycle
Meansigma methodss Xn of time.
That is, for single hard disk, as the average service time of I/O requests is the unit time
The meansigma methodss of the response time of the Z I/O request received in (such as 1s), then for single
For hard disk, the M that single hard disk is received in the current preset cycle (such as one hour) can be counted individual
I/O request response time, then by M each I/O ask response time be added, addition and again
The number of the I/O requests received within the current preset cycle divided by single hard disk, obtains current preset
Meansigma methodss Xn of the average service time of the corresponding I/O requests of single hard disk in cycle.
Optionally, in can also obtaining the unit interval in the current preset cycle, each hard disk is corresponding
The average service time sum of I/O requests, according to average service time sum and the number of unit interval
Ratio obtain the flat of the average service time of each hard disk corresponding I/O requests in the current preset cycle
Average Xn.For example, the unit interval is 1s, and predetermined period is one hour, then for single hard disk
For, the average service time of I/O that can be by single hard disk in a hour per 1s is added, then divided by
3600s, obtains the average service time of the corresponding I/O requests of single hard disk in the current preset cycle
Meansigma methodss Xn.
203rd, the quantity for obtaining the I/O requests that each hard disk correspondence is received in the current preset cycle is accounted for
The ratio of the total amount of the I/O requests that the corresponding all hard disks of the affiliated type of each hard disk are received.
Specifically, for single hard disk, its I/O received within the current preset cycle can be counted
Quantity Yn of request, for the hard disk of each type, all hard disks in each type is received
To I/O request quantity be added obtain each type hard disk I/O request total amount, then,
Hard disk to one type type, the single hard disk obtained in this type were received within the current preset cycle
To quantity Yn of I/O requests account for I/O requests that the corresponding all hard disks of this type receive
Ratio Zn of total amount.
204th, obtain current according to the meansigma methodss and ratio of each hard disk in different types of hard disk
The average service time of the corresponding I/O requests of different types of hard disk in predetermined period.
Specifically, the meansigma methodss of each hard disk in different types of hard disk and ratio can be weighted
Calculate when obtaining the average service of the corresponding I/O requests of different types of hard disk in the current preset cycle
Between.
Wherein, if the corresponding I/O of any type of hard disk in different types of hard disk requests it is average
It is expressed as AvgT service times, then AvgT=X1*Z1+X2*Z2+…Xn*Zn, X1Represent any kind
Hard disk in the 1st corresponding meansigma methodss of hard disk, Z1The 1st corresponding ratio of hard disk is represented,
X2Represent the 2nd corresponding meansigma methodss of hard disk in any type of hard disk, Z2Represent described
The corresponding ratio of 2 hard disks, XnRepresent that n-th hard disk in any type of hard disk is corresponding
Meansigma methodss, ZnRepresent the corresponding ratio of n-th hard disk.
If a hard disk receives more I/O requests here, its business is busier, then I/O
Weights of the big hard disk of pressure in the hard disk of its affiliated type are just higher.
205th, the average service time and preset value according to the corresponding I/O requests of different types of hard disk
The corresponding slow disk threshold value of the different types of hard disk of the next predetermined period of Relation acquisition.
Specifically, the definition according to the above-mentioned concept for slow disk, the corresponding I/O of different types of hard disk
The average service time of request and the relation of preset value can be the relation of product, and preset value for example can be with
For 10.
In the embodiment of the present invention, the determination of preset value can also be according to the fault-tolerant ability of array system come really
Fixed, fault-tolerant ability is higher, and preset value here is bigger.Predetermined period can be asked with the I/O of array system
The undulatory property asked determines that undulatory property is bigger, and predetermined period can arrange longer.
206th, according in the corresponding slow disk threshold value of different types of hard disk and next predetermined period, each is hard
The average service time of the corresponding I/O requests of disk determines the slow disk in next predetermined period.
In basis, the I/O requests situation in a cycle determines the corresponding slow disk threshold of different types of hard disk
After value, can be determined according to the corresponding slow disk threshold value of different types of hard disk in next predetermined period next
Slow disk in predetermined period.Specifically, for the hard disk of any of which type, can be according to one section
The average service time and the slow disk threshold of any type of hard disk of the I/O requests of each hard disk in time
Value is compared, for example, the average service time of single hard disk is calculated once per 5min, if the 5min
It is determined that single hard disk average service time more than or equal to its affiliated type hard disk slow disk threshold
Value, then determine that the single hard disk is slow disk.
207th, start slow disk data reconstruction, and send a warning message.
If certain hard disk is defined as slow disk, the data of the slow disk can be obtained by data reconstruction, and will
The data of the slow disk are transferred to another free hard disk, isolate the slow disk, and send a warning message to notify
Management personnel.
As the embodiment of the present invention is to do lateral comparison to the hard disk in array system, so for difference
Type of service, the response time of the I/O of the hard disk in array system be it is different, therefore, this
The slow disk detection mode of the bright embodiment also different type of service of self adaptation.Likewise, the clothes of hard disk
After the business time limit increases, the hard disk in array system just has aging, and the response time of its I/O mutually can be strained
Slowly, this lateral comparison of the embodiment of the present invention determines the mode of the slow disk also different lengths of service of self adaptation
Hard disk.
The embodiment of the present invention provides a kind of slow disk detection method, different in the current preset cycle by obtaining
The average service time of the corresponding input and output I/O requests of hard disk of type, further according to different types of
The average service time of the corresponding I/O requests of hard disk is with the next predetermined period of Relation acquisition of preset value not
The corresponding slow disk threshold value of hard disk of same type, and then according to the corresponding slow disk threshold value of different types of hard disk
The average service time of I/O requests corresponding with each hard disk in next predetermined period determines next default
Slow disk in cycle, thus, the present invention can be according to different types of hard disk in the current preset cycle
Average service time determines the slow disk threshold value of next predetermined period, so can be to different types of hard disk
Due to the different slow disk threshold values for formulating differentiation of the average service time of its I/O, also due to hard disk is not
I/O response times with type of service are different, the response time of the I/O of the hard disk of the different lengths of service
Also it is different, cause the average service time of the I/O of hard disk different so that this slow disk threshold value of the present invention
Differentiation determine do lateral comparison equivalent to the hard disk in system, therefore, different type of the present invention
The slow disk threshold value of differentiation also can adapt to the hard disk of different service types and the different lengths of service, energy
The differentiation of enough hard disks according to different hard disk types, different service types and the different lengths of service is solved
The low problem of slow disk detection degree of accuracy, improves the degree of accuracy of slow disk detection.
The embodiment of the present invention provides a kind of device 3 of slow disk detection, as shown in figure 3, including：
Acquiring unit 301, for obtaining the corresponding input of different types of hard disk in the current preset cycle
The average service time of output I/O requests；
Acquiring unit 301, is additionally operable to the average clothes according to the corresponding I/O requests of different types of hard disk
Business time slow disk threshold corresponding with the different types of hard disk of the next predetermined period of the Relation acquisition of preset value
Value；
Determining unit 302, for default with next according to the corresponding slow disk threshold value of different types of hard disk
The average service time of the corresponding I/O requests of each hard disk determines slow in next predetermined period in cycle
Disk.
Optionally, acquiring unit 301 can be specifically for：
Obtain the average of the average service time that the corresponding I/O of each hard disk is asked in the current preset cycle
Value；
It is hard that the quantity that the I/O that each hard disk correspondence is received in the acquisition current preset cycle is asked accounts for each
The ratio of the total amount of the I/O requests that the corresponding all hard disks of the affiliated type of disk are received；
Current preset is obtained according to the meansigma methodss and ratio of each hard disk in different types of hard disk
The average service time of the corresponding I/O requests of different types of hard disk in cycle.
Optionally, acquiring unit 301 can be specifically for：
Obtain the I/O requests that each hard disk correspondence is received in the current preset cycle response time it
With；
According to response time sum I/O requests number corresponding with each hard disk in the current preset cycle
Ratio obtains the average of the average service time of the corresponding I/O requests of each hard disk in the current preset cycle
Value.
Optionally, acquiring unit 301 can be specifically for：
Obtain the average clothes of the corresponding I/O requests of each hard disk in the unit interval in the current preset cycle
Business time sum；
The current preset cycle is obtained according to ratio of the average service time sum with the number of unit interval
The meansigma methodss of the average service time of the corresponding I/O requests of interior each hard disk.
Optionally, acquiring unit 301 can be specifically for：
The meansigma methodss and ratio of each hard disk in different types of hard disk are weighted into acquisition
The average service time of the corresponding I/O requests of different types of hard disk in the current preset cycle；
Wherein, if the corresponding I/O of any type of hard disk in different types of hard disk requests it is average
It is expressed as AvgT service times, then AvgT=X1*Z1+X2*Z2+…Xn*Zn, X1Represent any kind
Hard disk in the 1st corresponding meansigma methodss of hard disk, Z1The 1st corresponding ratio of hard disk is represented,
X2Represent the 2nd corresponding meansigma methodss of hard disk in any type of hard disk, Z2Represent described
The corresponding ratio of 2 hard disks, XnRepresent that n-th hard disk in any type of hard disk is corresponding
Meansigma methodss, ZnRepresent the corresponding ratio of n-th hard disk.
Optionally, acquiring unit 301 can be specifically for：
According to the product of the average service time and preset value of the corresponding I/O requests of different types of hard disk
Obtain the corresponding slow disk threshold value of the different types of hard disk of next predetermined period.
Optionally, determining unit 302 can be also used for：
It is in first predetermined period after electricity on storage array, corresponding just according to different types of hard disk
During the average service time of beginning threshold value I/O requests corresponding with each hard disk determines different types of hard disk
Slow disk.
The embodiment of the present invention provides a kind of device of slow disk detection, by obtaining in the current preset cycle not
The average service time of the corresponding input and output I/O requests of hard disk of same type, further according to different type
Hard disk corresponding I/O requests average service time and preset value the next predetermined period of Relation acquisition
The corresponding slow disk threshold value of different types of hard disk, and then according to the corresponding slow disk threshold of different types of hard disk
The average service time of value I/O requests corresponding with each hard disk in next predetermined period determines next pre-
If the slow disk in the cycle, thus, the present invention can be according to different types of hard disk in the current preset cycle
Average service time determine the slow disk threshold value of next predetermined period, so can be to different types of hard
Disk formulates the slow disk threshold values of differentiation due to the difference of the average service time of its I/O, also due to hard disk
The I/O response times of different service types are different, during the response of the I/O of the hard disk of the different lengths of service
Between it is also different, cause the average service time of the I/O of hard disk different so that this slow disk threshold of the present invention
The differentiation of value determines does lateral comparison equivalent to the hard disk in system, therefore, inhomogeneity of the present invention
The slow disk threshold value of the differentiation of type also can adapt to the hard disk of different service types and the different lengths of service,
Can be according to the difference neutralizing of the hard disk of different hard disk types, different service types and the different lengths of service
The low problem of certainly slow disk detection degree of accuracy, improves the degree of accuracy of slow disk detection.
The embodiment of the present invention provides a kind of detection means 4 of slow disk, as shown in figure 4, including：Storage
Device 401, processor 402 and communication bus 403.Wherein：Memorizer 401 is used for store instruction
And data, processor 402, for performing the instruction for obtaining different type in the current preset cycle
Hard disk corresponding input and output I/O requests average service time；According to different types of hard disk pair
The average service time of the I/O requests answered and the next predetermined period different type of Relation acquisition of preset value
The corresponding slow disk threshold value of hard disk；It is default with next according to the corresponding slow disk threshold value of different types of hard disk
In cycle, the average service time of each hard disk corresponding I/O requests determines slow in next predetermined period
Disk.The data of the storage of memorizer 401 include that different types of hard disk is corresponding defeated in the current preset cycle
Enter to export average service time, preset value and the different types of hard disk of next predetermined period of I/O requests
Corresponding slow disk threshold value etc..
In embodiments of the present invention, optionally, processor 402 is used to perform the acquisition current preset cycle
The average service time of the corresponding input and output I/O requests of interior different types of hard disk includes：
Obtain the average of the average service time that the corresponding I/O of each hard disk is asked in the current preset cycle
Value；
It is hard that the quantity that the I/O that each hard disk correspondence is received in the acquisition current preset cycle is asked accounts for each
The ratio of the total amount of the I/O requests that the corresponding all hard disks of the affiliated type of disk are received；
Current preset is obtained according to the meansigma methodss and ratio of each hard disk in different types of hard disk
The average service time of the corresponding I/O requests of different types of hard disk in cycle.
The data of the storage of memorizer 401 can also include above-mentioned meansigma methodss and ratio.
In embodiments of the present invention, optionally, processor 402 is used to perform the acquisition current preset cycle
The meansigma methodss of the average service time of the corresponding I/O requests of interior each hard disk include：
Obtain the I/O requests that each hard disk correspondence is received in the current preset cycle response time it
With；
According to response time sum I/O requests number corresponding with each hard disk in the current preset cycle
Ratio obtains the average of the average service time of the corresponding I/O requests of each hard disk in the current preset cycle
Value.
In embodiments of the present invention, optionally, processor 402 is used to perform the acquisition current preset cycle
The meansigma methodss of the average service time of the corresponding I/O requests of interior each hard disk include：
Obtain the average clothes of the corresponding I/O requests of each hard disk in the unit interval in the current preset cycle
Business time sum；
The current preset cycle is obtained according to ratio of the average service time sum with the number of unit interval
The meansigma methodss of the average service time of the corresponding I/O requests of interior each hard disk.
In embodiments of the present invention, optionally, processor 402 is used to perform according to different types of hard
The meansigma methodss of each hard disk in disk and ratio obtain different types of hard disk in the current preset cycle
The average service time of corresponding I/O requests includes：
The meansigma methodss and ratio of each hard disk in different types of hard disk are weighted into acquisition
The average service time of the corresponding I/O requests of different types of hard disk in the current preset cycle；
Wherein, if the corresponding I/O of any type of hard disk in different types of hard disk requests it is average
It is expressed as AvgT service times, then AvgT=X1*Z1+X2*Z2+…Xn*Zn, X1Represent any kind
Hard disk in the 1st corresponding meansigma methodss of hard disk, Z1The 1st corresponding ratio of hard disk is represented,
X2Represent the 2nd corresponding meansigma methodss of hard disk in any type of hard disk, Z2Represent described
The corresponding ratio of 2 hard disks, XnRepresent that n-th hard disk in any type of hard disk is corresponding
Meansigma methodss, ZnRepresent the corresponding ratio of n-th hard disk.
In embodiments of the present invention, optionally, processor 402 is used to perform according to different types of hard
The average service time of the corresponding I/O requests of disk is different from the next predetermined period of the Relation acquisition of preset value
The corresponding slow disk threshold value of hard disk of type includes：
According to the product of the average service time and preset value of the corresponding I/O requests of different types of hard disk
Obtain the corresponding slow disk threshold value of the different types of hard disk of next predetermined period.
In embodiments of the present invention, optionally, processor 402 is can be also used for for execute instruction：
It is in first predetermined period after electricity on storage array, corresponding just according to different types of hard disk
During the average service time of beginning threshold value I/O requests corresponding with each hard disk determines different types of hard disk
Slow disk.
The embodiment of the present invention provides a kind of device of slow disk detection, by obtaining in the current preset cycle not
The average service time of the corresponding input and output I/O requests of hard disk of same type, further according to different type
Hard disk corresponding I/O requests average service time and preset value the next predetermined period of Relation acquisition
The corresponding slow disk threshold value of different types of hard disk, and then according to the corresponding slow disk threshold of different types of hard disk
The average service time of value I/O requests corresponding with each hard disk in next predetermined period determines next pre-
If the slow disk in the cycle, thus, the present invention can be according to different types of hard disk in the current preset cycle
Average service time determine the slow disk threshold value of next predetermined period, so can be to different types of hard
Disk formulates the slow disk threshold values of differentiation due to the difference of the average service time of its I/O, also due to hard disk
The I/O response times of different service types are different, during the response of the I/O of the hard disk of the different lengths of service
Between it is also different, cause the average service time of the I/O of hard disk different so that this slow disk threshold of the present invention
The differentiation of value determines does lateral comparison equivalent to the hard disk in system, therefore, inhomogeneity of the present invention
The slow disk threshold value of the differentiation of type also can adapt to the hard disk of different service types and the different lengths of service,
Can be according to the difference neutralizing of the hard disk of different hard disk types, different service types and the different lengths of service
The low problem of certainly slow disk detection degree of accuracy, improves the degree of accuracy of slow disk detection.
In several embodiments provided herein, it should be understood that disclosed apparatus and method,
Can realize by another way.For example, device embodiment described above is only schematic
, for example, the division of the unit, only a kind of division of logic function can be with when actually realizing
Have other dividing mode, such as multiple units or component can with reference to or be desirably integrated into another
System, or some features can ignore, or do not perform.It is another, it is shown or discussed it is mutual it
Between coupling direct-coupling or communication connection can be by the indirect of some interfaces, device or unit
Coupling is communicated to connect, and can be electrical, mechanical or other forms.
It is described as separating component explanation unit can be or may not be it is physically separate,
As the part that unit shows can be or may not be physical location, you can with positioned at a ground
Side, or can also be distributed on multiple NEs.Can select therein according to the actual needs
Some or all of unit is realizing the purpose of this embodiment scheme.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit
In, or the independent physics of unit include, it is also possible to two or more units are integrated in
In one unit.Above-mentioned integrated unit both can be realized in the form of hardware, it would however also be possible to employ hard
Part adds the form of SFU software functional unit to realize.
The above-mentioned integrated unit realized in the form of SFU software functional unit, can be stored in a calculating
In machine read/write memory medium.Above-mentioned SFU software functional unit is stored in a storage medium, if including
Dry instruction is used so that a computer equipment (can be personal computer, server, or network
Equipment etc.) perform the part steps of each embodiment methods described of the invention.And aforesaid storage medium
Including：USB flash disk, portable hard drive, read only memory (Read-Only Memory, abbreviation ROM),
Random access memory (Random Access Memory, abbreviation RAM), magnetic disc or CD etc.
It is various can be with the medium of store program codes.
Finally it should be noted that：Above example is only illustrating technical scheme rather than right
Its restriction；Although being described in detail to the present invention with reference to the foregoing embodiments, this area it is common
Technical staff should be understood：Which still can be repaiied to the technical scheme described in foregoing embodiments
Change, or equivalent is carried out to which part technical characteristic；And these modifications or replacement, not
Make the spirit and scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution.
Claims (14)
1. a kind of slow disk detection method, it is characterised in that include：
Obtain the average of the corresponding input and output I/O requests of different types of hard disk in the current preset cycle
Service time；
According to the relation of the average service time and preset value of the corresponding I/O requests of different types of hard disk
Obtain the corresponding slow disk threshold value of the different types of hard disk of next predetermined period；
According to the corresponding slow disk threshold value of different types of hard disk and each hard disk in next predetermined period
The average service time of corresponding I/O requests determines the slow disk in next predetermined period.
2. method according to claim 1, it is characterised in that the acquisition current preset cycle
The average service time of the corresponding input and output I/O requests of interior different types of hard disk includes：
Obtain the average service time of the corresponding I/O requests of each hard disk in the current preset cycle
Meansigma methodss；
Obtain the quantity of the I/O requests that described each hard disk correspondence is received in the current preset cycle
Account for the ratio of the total amount of the I/O requests that the corresponding all hard disks of the affiliated type of described each hard disk are received；
Institute is obtained according to the meansigma methodss and the ratio of each hard disk in different types of hard disk
State the average service time of the corresponding I/O requests of different types of hard disk in the current preset cycle.
3. method according to claim 2, it is characterised in that the acquisition current preset
In cycle, the meansigma methodss of the average service time of the corresponding I/O requests of each hard disk include：
Obtain the response of the I/O requests that described each hard disk correspondence is received in the current preset cycle
Time sum；
According to the corresponding I/O of the response time sum each hard disk described in the current preset cycle
The ratio of request number obtains the average of the corresponding I/O requests of each hard disk in the current preset cycle
The meansigma methodss of service time.
4. method according to claim 2, it is characterised in that the acquisition current preset
In cycle, the meansigma methodss of the average service time of the corresponding I/O requests of each hard disk include：
The corresponding I/O requests of each hard disk described in obtaining in the unit interval in the current preset cycle
Average service time sum；
According to the ratio of the average service time sum and the number of the unit interval obtain it is described ought
The meansigma methodss of the average service time of the corresponding I/O requests of each hard disk in front predetermined period.
5. the method according to any one of claim 2-4, it is characterised in that described according to difference
The meansigma methodss of each hard disk in the hard disk of type and the ratio obtain the current preset week
In phase, the average service time of the corresponding I/O requests of different types of hard disk includes：
The meansigma methodss of each hard disk in different types of hard disk and the ratio are weighted and are obtained
Take the average service time of the corresponding I/O requests of different types of hard disk in the current preset cycle；
Wherein, if the average clothes of the corresponding I/O requests of any type of hard disk in different types of hard disk
The business time is expressed as AvgT, then AvgT=X1*Z1+X2*Z2+…Xn*Zn, X1Represent described any type of hard
The 1st corresponding meansigma methodss of hard disk in disk, Z1Represent the 1st corresponding ratio of hard disk, X2Table
Show the 2nd corresponding meansigma methodss of hard disk in any type of hard disk, Z2Represent described 2nd firmly
The corresponding ratio of disk, XnThe corresponding meansigma methodss of n-th hard disk in any type of hard disk are represented,
ZnRepresent the corresponding ratio of n-th hard disk.
6. method according to claim 1, it is characterised in that described according to different types of hard
The average service time of the corresponding I/O requests of disk is different from the next predetermined period of the Relation acquisition of preset value
The corresponding slow disk threshold value of hard disk of type includes：
According to the product of the average service time and preset value of the corresponding I/O requests of different types of hard disk
Obtain the corresponding slow disk threshold value of the different types of hard disk of next predetermined period.
7. method according to claim 1, it is characterised in that methods described also includes：
It is in first predetermined period after electricity on storage array, corresponding initial according to different types of hard disk
The average service time of threshold value I/O requests corresponding with described each hard disk determines different types of hard disk
In slow disk.
8. the device that a kind of slow disk is detected, it is characterised in that include：
Acquiring unit, for obtaining the corresponding input and output of different types of hard disk in the current preset cycle
The average service time of I/O requests；
The acquiring unit, is additionally operable to the average service according to the corresponding I/O requests of different types of hard disk
Time slow disk threshold value corresponding with the different types of hard disk of the next predetermined period of the Relation acquisition of preset value；
Determining unit, for according to the corresponding slow disk threshold value of different types of hard disk and next default week
During the average service time of the corresponding I/O requests of interim each hard disk determines next predetermined period
Slow disk.
9. device according to claim 8, it is characterised in that the acquiring unit specifically for：
Obtain the average service time of the corresponding I/O requests of each hard disk in the current preset cycle
Meansigma methodss；
Obtain the quantity of the I/O requests that described each hard disk correspondence is received in the current preset cycle
Account for the ratio of the total amount of the I/O requests that the corresponding all hard disks of the affiliated type of described each hard disk are received；
Institute is obtained according to the meansigma methodss and the ratio of each hard disk in different types of hard disk
State the average service time of the corresponding I/O requests of different types of hard disk in the current preset cycle.
10. device according to claim 9, it is characterised in that the acquiring unit specifically for：
Obtain the response of the I/O requests that described each hard disk correspondence is received in the current preset cycle
Time sum；
According to the corresponding I/O of the response time sum each hard disk described in the current preset cycle
The ratio of request number obtains the average of the corresponding I/O requests of each hard disk in the current preset cycle
The meansigma methodss of service time.
11. devices according to claim 9, it is characterised in that the acquiring unit specifically for：
The corresponding I/O requests of each hard disk described in obtaining in the unit interval in the current preset cycle
Average service time sum；
According to the ratio of the average service time sum and the number of the unit interval obtain it is described ought
The meansigma methodss of the average service time of the corresponding I/O requests of each hard disk in front predetermined period.
12. devices according to any one of claim 9-11, it is characterised in that the acquisition list
Unit specifically for：
The meansigma methodss of each hard disk in different types of hard disk and the ratio are weighted and are obtained
Take the average service time of the corresponding I/O requests of different types of hard disk in the current preset cycle；
Wherein, if the average clothes of the corresponding I/O requests of any type of hard disk in different types of hard disk
The business time is expressed as AvgT, then AvgT=X1*Z1+X2*Z2+…Xn*Zn, X1Represent described any type of hard
The 1st corresponding meansigma methodss of hard disk in disk, Z1Represent the 1st corresponding ratio of hard disk, X2Table
Show the 2nd corresponding meansigma methodss of hard disk in any type of hard disk, Z2Represent described 2nd firmly
The corresponding ratio of disk, XnThe corresponding meansigma methodss of n-th hard disk in any type of hard disk are represented,
ZnRepresent the corresponding ratio of n-th hard disk.
13. devices according to claim 8, it is characterised in that the acquiring unit specifically for：
According to the product of the average service time and preset value of the corresponding I/O requests of different types of hard disk
Obtain the corresponding slow disk threshold value of the different types of hard disk of next predetermined period.
14. devices according to claim 8, it is characterised in that the determining unit is additionally operable to：
It is in first predetermined period after electricity on storage array, corresponding initial according to different types of hard disk
The average service time of threshold value I/O requests corresponding with described each hard disk determines different types of hard disk
In slow disk.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510634651.0A CN106557389B (en) | 2015-09-29 | 2015-09-29 | A kind of slow disk detection method and device |
| PCT/CN2016/100133 WO2017054690A1 (en) | 2015-09-29 | 2016-09-26 | Method and device for detecting slow disk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510634651.0A CN106557389B (en) | 2015-09-29 | 2015-09-29 | A kind of slow disk detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106557389A true CN106557389A (en) | 2017-04-05 |
| CN106557389B CN106557389B (en) | 2019-03-08 |
Family
ID=58414841
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510634651.0A Active CN106557389B (en) | 2015-09-29 | 2015-09-29 | A kind of slow disk detection method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106557389B (en) |
| WO (1) | WO2017054690A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108319527A (en) * | 2017-12-21 | 2018-07-24 | 创新科存储技术（深圳）有限公司 | A kind of bad track disk detection method and device |
| CN109032851A (en) * | 2018-06-26 | 2018-12-18 | 华为技术有限公司 | A kind of link failure determines method and apparatus |
| WO2019101087A1 (en) * | 2017-11-22 | 2019-05-31 | 华为技术有限公司 | Slow-disk detection method, and storage array |
| CN112241343A (en) * | 2019-07-19 | 2021-01-19 | 深信服科技股份有限公司 | Slow disk detection method and device, electronic equipment and readable storage medium |
| CN112579379A (en) * | 2020-12-24 | 2021-03-30 | 深信服科技股份有限公司 | Method, system and device for identifying and processing slow card disc and readable storage medium |
| CN114415973A (en) * | 2022-03-28 | 2022-04-29 | 阿里云计算有限公司 | Slow disk detection method and device, electronic equipment and storage medium |
| CN115934003A (en) * | 2023-03-09 | 2023-04-07 | 浪潮电子信息产业股份有限公司 | Slow disk identification method, device and equipment in disk array and readable storage medium |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114327266B (en) * | 2021-12-24 | 2024-04-09 | 深信服科技股份有限公司 | Method, device and medium for slowly identifying card of storage device |
| CN116149894B (en) * | 2023-02-28 | 2023-10-27 | 哈尔滨工业大学（深圳） | Method for detecting slow card and related equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070101187A1 (en) * | 2005-10-28 | 2007-05-03 | Fujitsu Limited | RAID system, RAID controller and rebuilt/copy back processing method thereof |
| CN102147708A (en) * | 2010-02-10 | 2011-08-10 | 成都市华为赛门铁克科技有限公司 | Method and device for detecting discs |
| CN102568522A (en) * | 2011-12-31 | 2012-07-11 | 曙光信息产业股份有限公司 | Hardware performance test method and device |
| CN103488544A (en) * | 2013-09-26 | 2014-01-01 | 华为技术有限公司 | Processing method and device for detecting slow disk |
| CN103810062A (en) * | 2014-03-05 | 2014-05-21 | 华为技术有限公司 | Slow disk detection method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102279775B (en) * | 2011-08-19 | 2013-04-17 | 西安交通大学 | Method for processing failure of hard disk under Linux system |
| CN103793292A (en) * | 2012-11-03 | 2014-05-14 | 上海欧朋软件有限公司 | Disaster recovery method for disk array |
| US9135096B2 (en) * | 2012-12-06 | 2015-09-15 | Compellent Technologies | RAID surveyor |
-
2015
- 2015-09-29 CN CN201510634651.0A patent/CN106557389B/en active Active
-
2016
- 2016-09-26 WO PCT/CN2016/100133 patent/WO2017054690A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070101187A1 (en) * | 2005-10-28 | 2007-05-03 | Fujitsu Limited | RAID system, RAID controller and rebuilt/copy back processing method thereof |
| CN102147708A (en) * | 2010-02-10 | 2011-08-10 | 成都市华为赛门铁克科技有限公司 | Method and device for detecting discs |
| CN102568522A (en) * | 2011-12-31 | 2012-07-11 | 曙光信息产业股份有限公司 | Hardware performance test method and device |
| CN103488544A (en) * | 2013-09-26 | 2014-01-01 | 华为技术有限公司 | Processing method and device for detecting slow disk |
| CN103810062A (en) * | 2014-03-05 | 2014-05-21 | 华为技术有限公司 | Slow disk detection method and device |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019101087A1 (en) * | 2017-11-22 | 2019-05-31 | 华为技术有限公司 | Slow-disk detection method, and storage array |
| CN108319527A (en) * | 2017-12-21 | 2018-07-24 | 创新科存储技术（深圳）有限公司 | A kind of bad track disk detection method and device |
| CN109032851A (en) * | 2018-06-26 | 2018-12-18 | 华为技术有限公司 | A kind of link failure determines method and apparatus |
| CN109032851B (en) * | 2018-06-26 | 2021-01-12 | 华为技术有限公司 | Link fault determination method and device |
| CN112241343A (en) * | 2019-07-19 | 2021-01-19 | 深信服科技股份有限公司 | Slow disk detection method and device, electronic equipment and readable storage medium |
| CN112241343B (en) * | 2019-07-19 | 2024-02-23 | 深信服科技股份有限公司 | Slow disk detection method and device, electronic equipment and readable storage medium |
| CN112579379A (en) * | 2020-12-24 | 2021-03-30 | 深信服科技股份有限公司 | Method, system and device for identifying and processing slow card disc and readable storage medium |
| CN112579379B (en) * | 2020-12-24 | 2024-02-23 | 深信服科技股份有限公司 | Card slow disc identification processing method, system and device and readable storage medium |
| CN114415973A (en) * | 2022-03-28 | 2022-04-29 | 阿里云计算有限公司 | Slow disk detection method and device, electronic equipment and storage medium |
| CN115934003A (en) * | 2023-03-09 | 2023-04-07 | 浪潮电子信息产业股份有限公司 | Slow disk identification method, device and equipment in disk array and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106557389B (en) | 2019-03-08 |
| WO2017054690A1 (en) | 2017-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106557389A (en) | A kind of slow disk detection method and device | |
| CN103810062B (en) | Slow dish detection method and device | |
| US11036572B2 (en) | Method, device, and computer program product for facilitating prediction of disk failure | |
| US20180157438A1 (en) | Slow-disk detection method and apparatus | |
| CN104583930B (en) | Method, controller and the data migration device of Data Migration | |
| US11199968B2 (en) | Using recurring write quotas to optimize utilization of solid state storage in a hybrid storage array | |
| CN103218270B (en) | There is the computer of multiple solid-state disk | |
| CN103000228A (en) | Storage device test method and system | |
| JP2012523599A5 (en) | ||
| CN103150261B (en) | Method and device for simultaneously accessing multiple solid-state disks | |
| CN106354590A (en) | Method and apparatus for disk detection | |
| CN103176858B (en) | Storage device with multiple solid-state discs | |
| US10324794B2 (en) | Method for storage management and storage device | |
| CN105487823A (en) | Data migration method and device | |
| US11385828B2 (en) | Method and apparatus for calculating storage system available capacity | |
| CN103577115A (en) | Data configuration processing method and data configuration processing device | |
| CN103699340B (en) | A kind of request processing method and equipment | |
| CN106980468A (en) | Trigger the method and device that RAID array is rebuild | |
| CN103577337A (en) | Space allocation method and device for storage system | |
| CN109542503B (en) | Method and system for optimizing compatibility of storage link | |
| CN106990918A (en) | Trigger the method and device that RAID array is rebuild | |
| CN107678894A (en) | A kind of internal storage testing method, apparatus and system | |
| CN105528315B (en) | A kind of hard disk IO manufacture timeout control methods and device | |
| CN104424603A (en) | Method and device for metering power consumption in power distribution network | |
| CN107886992A (en) | A kind of RAID method for detecting health status, system and relevant apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |